Update README.md
Browse files
README.md
CHANGED
@@ -1,17 +1,48 @@
|
|
1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
base_model:
|
3 |
- davzoku/cria-llama2-7b-v1.3
|
4 |
library_name: transformers
|
5 |
tags:
|
6 |
- mergekit
|
7 |
- merge
|
|
|
8 |
|
9 |
---
|
10 |
-
#
|
11 |
|
12 |
-
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
13 |
|
14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
### Merge Method
|
16 |
|
17 |
This model was merged using the passthrough merge method.
|
@@ -23,7 +54,8 @@ The following models were included in the merge:
|
|
23 |
|
24 |
### Configuration
|
25 |
|
26 |
-
The following YAML configuration was used to produce this model
|
|
|
27 |
|
28 |
```yaml
|
29 |
# https://huggingface.co/Undi95/Mistral-11B-v0.1
|
|
|
1 |
---
|
2 |
+
inference: false
|
3 |
+
language: en
|
4 |
+
license: llama2
|
5 |
+
model_type: llama
|
6 |
+
datasets:
|
7 |
+
- mlabonne/CodeLlama-2-20k
|
8 |
+
pipeline_tag: text-generation
|
9 |
base_model:
|
10 |
- davzoku/cria-llama2-7b-v1.3
|
11 |
library_name: transformers
|
12 |
tags:
|
13 |
- mergekit
|
14 |
- merge
|
15 |
+
- llama-2
|
16 |
|
17 |
---
|
18 |
+
# FrankenCRIA v1.3-m.1
|
19 |
|
|
|
20 |
|
21 |
+
|
22 |
+
## What is FrankenCRIA?
|
23 |
+
|
24 |
+
> krē-ə plural crias. : a baby llama, alpaca, vicuña, or guanaco.
|
25 |
+
|
26 |
+
<p align="center">
|
27 |
+
<img src="https://raw.githubusercontent.com/davzoku/cria/main/assets/" width="300" height="300" alt="FrankenCRIA Logo"> <br>
|
28 |
+
<i>This is a frankenmerge of [davzoku/cria-llama2-7b-v1.3](https://huggingface.co/davzoku/cria-llama2-7b-v1.3) created using [mergekit](https://github.com/cg123/mergekit).</i>
|
29 |
+
</p>
|
30 |
+
|
31 |
+
This configuration is the same as [Undi95/Mistral-11B-v0.1](https://huggingface.co/Undi95/Mistral-11B-v0.1), [mlabonne/FrankenBeagle14-11B](https://huggingface.co/mlabonne/FrankenBeagle14-11B) and the DUS technique used in [upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0).
|
32 |
+
|
33 |
+
|
34 |
+
Please be aware that this model is highly experimental, and no further training has been conducted following the merge.
|
35 |
+
Therefore, the model performance may not meet expectations, as described in the [SOLAR paper](https://arxiv.org/abs/2312.15166)
|
36 |
+
|
37 |
+
## 📦 FrankenCRIA Model Release
|
38 |
+
|
39 |
+
FrankenCRIA v1.3 comes with several variants.
|
40 |
+
|
41 |
+
- [davzoku/frankencria-llama2-11b-v1.3-m.1](https://huggingface.co/davzoku/frankencria-llama2-11b-v1.3-m.1): 11B FrankenMerge inspired by [Undi95/Mistral-11B-v0.1](https://huggingface.co/Undi95/Mistral-11B-v0.1)
|
42 |
+
- [davzoku/frankencria-llama2-11b-v1.3-m.2](https://huggingface.co/davzoku/frankencria-llama2-12.5b-v1.3-m.2): 12.5B interleaving FrankenMerge inspired by [vilm/vinallama-12.5b-chat-DUS](https://huggingface.co/vilm/vinallama-12.5b-chat-DUS)
|
43 |
+
|
44 |
+
|
45 |
+
## 🧩 Merge Details
|
46 |
### Merge Method
|
47 |
|
48 |
This model was merged using the passthrough merge method.
|
|
|
54 |
|
55 |
### Configuration
|
56 |
|
57 |
+
The following YAML configuration was used to produce this model.
|
58 |
+
|
59 |
|
60 |
```yaml
|
61 |
# https://huggingface.co/Undi95/Mistral-11B-v0.1
|